®®®® SIIA Público

Título del libro: 2013 10th International Conference On Electrical Engineering, Computing Science And Automatic Control (cce)
Título del capítulo: An Efficient Color Descriptor Based on Global and Local Color Features for Image Retrieval

Autores UNAM:
MANUEL CEDILLO HERNANDEZ; FRANCISCO JAVIER GARCIA UGALDE;
Autores externos:
Idioma:
Año de publicación:
2013
Palabras clave:

CBIR; image retrieval; color-based descriptor; color correlogram; histogram intersection; dominant color; image indexing

Resumen:

In the context of content-based image retrieval (CBIR) problem, an image is represented by feature vectors called descriptors, whose efficiency is essential to obtain a good performance in the image indexing and retrieval tasks. In this paper, we propose an algorithm to obtain an efficient color-based descriptor, which is a combination of Color Correlogram (CC) and Dominant Color (DC). The color-based descriptors, such as Histogram Intersection (HI) and DC take into account the global distribution of color in an image, while CC takes into account the local color distribution. So the combination of global and local color distribution provides a good image description. By its design, the proposed descriptor is more compact compared with the CC descriptor, which allows reducing computational complexity. Using the Average Retrieval precision (ARP) with different factors the effectiveness of the proposed descriptor is evaluated and compared with the conventional color-based descriptors, such as HI, CC and DC. The image database used in this work contains 500 images with 25 categories randomly selected from the Corel Dataset.

Entidades citadas de la UNAM:
Fuente:


ISBN:
9781479914609
Editorial:
IEEE

Tipo de producto:
Proceedings Paper